Candidate Genes from an FDA-Approved Algorithm Fail to Predict Opioid Use Disorder Risk in Over 450,000 Veterans

• Published in: bioRxiv (Cold Spring Harbor Laboratory)
• Main Authors: Davis, Christal N, Jinwala, Zeal, Hatoum, Alexander S, Toikumo, Sylvanus, Agrawal, Arpana, Rentsch, Christopher T, Edenberg, Howard J, Baurley, James W, Hartwell, Emily E, Crist, Richard C, Gray, Joshua C, Justice, Amy C, Gelernter, Joel, Kember, Rachel L, Kranzler, Henry R
• Format: Journal Article
• Language: English
• Published: United States 16.05.2024
• DOI: 10.1101/2024.05.16.24307486

Recently, the Food and Drug Administration gave pre-marketing approval to algorithm based on its purported ability to identify genetic risk for opioid use disorder. However, the clinical utility of the candidate genes comprising the algorithm has not been independently demonstrated. To assess the utility of 15 variants in candidate genes from an algorithm intended to predict opioid use disorder risk. This case-control study examined the association of 15 candidate genetic variants with risk of opioid use disorder using available electronic health record data from December 20, 1992 to September 30, 2022. Electronic health record data, including pharmacy records, from Million Veteran Program participants across the United States. Participants were opioid-exposed individuals enrolled in the Million Veteran Program (n = 452,664). Opioid use disorder cases were identified using International Classification of Disease diagnostic codes, and controls were individuals with no opioid use disorder diagnosis. Number of risk alleles present across 15 candidate genetic variants. Predictive performance of 15 genetic variants for opioid use disorder risk assessed via logistic regression and machine learning models. Opioid exposed individuals (n=33,669 cases) were on average 61.15 (SD = 13.37) years old, 90.46% male, and had varied genetic similarity to global reference panels. Collectively, the 15 candidate genetic variants accounted for 0.4% of variation in opioid use disorder risk. The accuracy of the ensemble machine learning model using the 15 genes as predictors was 52.8% (95% CI = 52.1 - 53.6%) in an independent testing sample. Candidate genes that comprise the approved algorithm do not meet reasonable standards of efficacy in predicting opioid use disorder risk. Given the algorithm's limited predictive accuracy, its use in clinical care would lead to high rates of false positive and negative findings. More clinically useful models are needed to identify individuals at risk of developing opioid use disorder.